BC skill-vetter
Security vetting protocol before installing any AI agent skill. Red flag detection for credential theft, obfuscated code, exfiltration. Risk classification LOW/MEDIUM/HIGH/EXTREME. Produces structured vetting reports. Never install untrusted skills without running this first.
Security vetting protocol before installing any AI agent skill.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 3
-
high Dangerous commands
cmd-encoded-execSKILL.md:262Executes a base64/encoded payload (documentation of a security skill)eval $(echo "Y3Vy…zaA==" | base64 -d)
security skill
Medium and low: 2
-
low Risky intent
intent-offensive-securitySKILL.md:105Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- [ ] No credential harvesting patterns
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (skill-vetter) differs from the folder (openclaw-skill-vetter)
- 100Tools and files. No external tools needed
- 100Steps. 38 steps
- 100Execution cost. Instruction body is 2133 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low 13 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -214 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 276: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 38 items
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.